Digital Forensics for AI: When the Model Becomes the Crime Scene

You must register and pay to attend:
https://www.eventbrite.com/e/digital-forensics-for-ai-when-the-model-becomes-the-crime-scene-tickets-1987788998404

### Topic One: Digital Forensics for AI: When the Model Becomes the Crime Scene

Artificial intelligence systems have become increasingly embedded in critical business, security, and decision-making processes; they are no longer just tools—they are potential targets, witnesses, and even victims of cyber incidents. Traditional digital forensics methods were designed for static systems and deterministic software, but AI introduces a new paradigm where models themselves can be manipulated, poisoned, or exploited in ways that leave complex and often non-obvious traces.

This presentation explores the emerging discipline of AI-focused digital forensics, where the model becomes the crime scene. We will examine how adversaries attack machine learning systems through techniques such as data poisoning, model inversion, and adversarial inputs, and what forensic artifacts these attacks leave behind. Attendees will gain insight into how to investigate compromised models, validate model integrity, and reconstruct attack timelines in environments where behavior is probabilistic rather than deterministic.

The session will also address practical challenges, including lack of logging visibility, reproducibility issues, and the difficulty of distinguishing model drift from malicious tampering. Real-world scenarios and case studies will illustrate how organizations can build forensic readiness into their AI pipelines, leveraging secure MLOps practices, auditability, and governance frameworks.

By the end of this talk, participants will understand how to extend traditional forensic methodologies into AI-driven environments, enabling them to detect, investigate, and respond to incidents where the model itself holds the evidence.

Speaker One: Genevieve McGinty

Genevieve McGinty is a cybersecurity and digital forensics practitioner & strategist with more than two decades of experience protecting critical infrastructure, corporate networks, and healthcare systems. As the Founder & CEO of Intelligent ForensicsX, Inc., she leads initiatives in cyber risk management, threat intelligence, and forensic analysis—helping organizations uncover digital evidence, strengthen defenses, and ensure regulatory compliance.

Her career spans leadership roles across global enterprises and public agencies, including the SAIC, Large Hospitals, PVH Corp (Retail), Atos North America, and several local & state legal firms. Genevieve has successfully directed large-scale security operations, incident response programs, and strategic initiatives that align cybersecurity with business objectives.

Known for her analytical insight and commitment to operational excellence, Genevieve is a trusted advisor to executives and legal teams seeking clarity in complex security initiatives and digital investigations. Her work bridges technology, governance, and leadership—empowering organizations to anticipate threats, respond decisively, and build lasting cyber resilience in an evolving digital landscape.

### Topic Two: The Insider Isn’t Human: Securing AI Agents as the Newest Insider Threat

As organizations increasingly deploy AI agents to act autonomously across security, IT, and business workflows, the definition of “insider” is rapidly changing. Hear how AI agents that are often highly privileged, always active, and operating at machine speed, introduce a new class of insider risk that traditional security models are not designed to detect.

Attendees will learn why static rules and alert‑driven approaches fall short for agent activity, how behavioral intelligence provides the missing context to identify abnormal or risky behavior, and what it means to extend insider‑threat detection and investigation beyond humans to include AI systems themselves.

### Speaker Two: Steve Wilson

Steve Wilson is the Chief AI and Product Officer at Exabeam, where his team applies cutting-edge AI technologies to tackle real-world cybersecurity challenges. He founded and co-chairs the OWASP Gen AI Security Project, the organization behind the industry-standard OWASP Top 10 for Large Language Model Security list.

His award-winning book, "The Developer’s Playbook for Large Language Model Security" (O'Reilly Media), was selected as the best Cutting Edge Cybersecurity Book by Cyber Defense Magazine.

Steve contributed to the development of Java at Sun Microsystems and held leadership positions at industry giants Citrix and Oracle. He holds 11 U.S. and international patents, and was named a Cybersecurity Innovation Leader by Enterprise Security Tech.